#58 DeepSeek V4 Pro
none
SVG tidak valid
- Biaya
- $0.000
- Waktu
- 300.0s
- Token
- 0 tok
AI BENCHY Compare
DeepSeek: DeepSeek V4 Pro vs Xiaomi: MiMo-V2.5-Pro
Ringkasan
Perbandingan benchmark DeepSeek V4 Pro vs MiMo-V2.5-Pro: MiMo-V2.5-Pro unggul dalam skor rata-rata dengan 7.4 vs 7.2. DeepSeek V4 Pro memiliki biaya benchmark lebih rendah di $0.034 vs $0.106. DeepSeek V4 Pro lebih cepat di 6.41s vs 26.13s, dengan tingkat keberhasilan 52.4% vs 68.3%.
Model yang direkomendasikan: DeepSeek V4 Pro - Its score stays close to the best score here (7.2 vs 7.4), while costing about 3.2x less than MiMo-V2.5-Pro.
Benchmark dihasilkan dari suite pengujian AI BENCHY pada: 2026-06-18
| Metrik | DeepSeek V4 Pro DeepSeek V4 Pro none | MiMo-V2.5-Pro MiMo-V2.5-Pro medium |
|---|---|---|
| Skor | 7.2 | 7.4 |
| Peringkat | #58 | #51 |
| Keandalan | 9.9 | 10.0 |
| Konsistensi | 8.8 | 8.5 |
| Tes benar | ||
| Tingkat lulus per percobaan | 52.4% | 68.3% |
| Tes tidak stabil | 3 | 4 |
| Total Run | 63 | 63 |
| Biaya per hasil | 0.333 | 2.541 |
| Total Biaya | $0.034 | $0.106 |
| Harga input | $0.435 / 1M | $0.435 / 1M |
| Harga output | $0.870 / 1M | $0.870 / 1M |
| Total token input | 53,558 | 40,854 |
| Token output | 11,424 | 5,015 |
| Token penalaran | 0 | 97,742 |
| Waktu respons (rata-rata) | 6.41s | 26.13s |
| Waktu respons (maks) | 30.09s | 130.77s |
| Waktu respons (total) | 134.66s | 548.65s |
Showcase generasi
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#51 MiMo-V2.5-Pro
medium
SVG tidak valid
- Biaya
- $0.000
- Waktu
- 300.0s
- Token
- 0 tok
Model teratas berdasarkan skor
Skor vs Total Biaya
Waktu respons (rata-rata)
Skor vs Waktu respons (rata-rata)
Total token output
Skor vs Total token output
Rincian Kategori
| Trik anti-AI | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro | 3.2 | 6.1 | 16.7% | 2 | 4.02s | 540 | 1,168 | 0 | |
| MiMo-V2.5-Pro | 10.0 | 10.0 | 100.0% | 0 | 3.26s | 621 | 323 | 1,179 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro | 5.6 | 10.0 | 33.3% | 0 | 13.38s | 7,275 | 5,500 | 0 | |
| MiMo-V2.5-Pro | 6.2 | 4.7 | 66.7% | 2 | 92.07s | 6,543 | 780 | 51,218 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro | 9.5 | 10.0 | 100.0% | 0 | 23.74s | 27,529 | 2,235 | 0 | |
| MiMo-V2.5-Pro | 10.0 | 10.0 | 100.0% | 0 | 53.36s | 15,060 | 348 | 11,870 |
| Parsing dan ekstraksi data | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro | 10.0 | 10.0 | 100.0% | 0 | 4.61s | 7,568 | 200 | 0 | |
| MiMo-V2.5-Pro | 7.3 | 5.8 | 83.3% | 1 | 18.81s | 7,746 | 260 | 8,383 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro | 5.3 | 10.0 | 33.3% | 0 | 3.72s | 666 | 24 | 0 | |
| MiMo-V2.5-Pro | 5.3 | 10.0 | 33.3% | 0 | 37.87s | 630 | 275 | 17,023 |
| Kecerdasan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro | 5.0 | 10.0 | 0.0% | 0 | 2.05s | 471 | 126 | 0 | |
| MiMo-V2.5-Pro | 5.5 | 10.0 | 0.0% | 0 | 4.02s | 492 | 155 | 163 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro | 6.3 | 5.8 | 66.7% | 1 | 4.12s | 627 | 713 | 0 | |
| MiMo-V2.5-Pro | 9.9 | 10.0 | 100.0% | 0 | 2.77s | 672 | 82 | 803 |
| Pemecahan teka-teki | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro | 10.0 | 10.0 | 100.0% | 0 | 3.61s | 594 | 442 | 0 | |
| MiMo-V2.5-Pro | 6.7 | 7.9 | 55.6% | 1 | 5.31s | 660 | 540 | 2,181 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro | 10.0 | 10.0 | 100.0% | 0 | 7.40s | 8,105 | 328 | 0 | |
| MiMo-V2.5-Pro | 10.0 | 10.0 | 100.0% | 0 | 16.87s | 8,220 | 311 | 2,908 |
| Pengetahuan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro | 3.0 | 10.0 | 0.0% | 0 | 5.76s | 183 | 688 | 0 | |
| MiMo-V2.5-Pro | 3.0 | 10.0 | 0.0% | 0 | 12.46s | 210 | 1,941 | 2,014 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
DeepSeek V4 PrononevsGemma 4 26B A4BmediumTersedia gratisGemini 3 Flash PreviewlowvsMiMo-V2.5-PromediumDeepSeek V4 PrononevsStep 3.7 FlashhighDeepSeek V4 PrononevsGLM 5.1mediumGPT-5.3 ChatnonevsMiMo-V2.5-PromediumClaude Sonnet 4.6nonevsMiMo-V2.5-PromediumDeepSeek V4 PrononevsKimi K2.7 CodemediumDeepSeek V4 PrononevsGrok 4.20mediumClaude Opus 4.8nonevsMiMo-V2.5-PromediumDeepSeek V4 ProhighvsMiMo-V2.5-PromediumDeepSeek V4 PrononevsGemini 3 Flash PreviewlowSeed-2.0-MinimediumvsDeepSeek V4 Pronone